REPORT Asaei_Idiap-RR-22-2011/IDIAP Multi-party Speech Recovery Exploiting Structured Sparsity Models Asaei, Afsaneh Taghizadeh, Mohammad J. Bourlard, Hervé Cevher, Volkan Image Model speech sparsity structured sparsity models un- derdetermined convolutive speech separation EXTERNAL https://publications.idiap.ch/attachments/reports/2011/Asaei_Idiap-RR-22-2011.pdf PUBLIC Idiap-RR-22-2011 2011 Idiap July 2011 We study the sparsity of spectro-temporal representation of speech in reverberant acoustic conditions. This study motivates the use of structured sparsity models for efficient recovery of speech. We formulate the underdetermined convolutive speech separation in spectro-temporal domain as the sparse signal recovery where we leverage model-based recovery algorithms. To tackle the ambiguity of the real acoustics, we exploit the Image Model of the enclosures to estimate the room impulse response function through a structured sparsity constraint optimization. The experiments conducted on real data recordings demonstrate the effectiveness of the proposed approach for multi-party speech applications.